I did a fresh clone of the official SD repo today and setup a fresh conda environment. When I added the optimizedSD folder and I try to run it I get the following. Any ideas how to resolve this?
I get this when running any of the py in optimizedSD
python optimizedSD/txt2img_gradio.py
python optimizedSD/optimized_txt2img.py
etc
Loading model from models/ldm/stable-diffusion-v1/model.ckpt
Global Step: 470000
Traceback (most recent call last):
File "optimizedSD/txt2img_gradio.py", line 66, in
model = instantiate_from_config(config.modelUNet)
File "/mnt/e/StableDiffusion/stable-diffusion/ldm/util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "/mnt/e/StableDiffusion/stable-diffusion/ldm/util.py", line 93, in get_obj_from_str
return getattr(importlib.import_module(module, package=None), cls)
File "/home/samuel/anaconda3/envs/ldm/lib/python3.8/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1014, in _gcd_import
File "", line 991, in _find_and_load
File "", line 975, in _find_and_load_unlocked
File "", line 671, in _load_unlocked
File "", line 783, in exec_module
File "", line 219, in _call_with_frames_removed
File "/mnt/e/StableDiffusion/stable-diffusion/optimizedSD/ddpm.py", line 15, in
from ldm.models.autoencoder import VQModelInterface
File "/mnt/e/StableDiffusion/stable-diffusion/ldm/models/autoencoder.py", line 6, in
from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer
ImportError: cannot import name 'VectorQuantizer2' from 'taming.modules.vqvae.quantize' (/home/samuel/anaconda3/envs/ldm/lib/python3.8/site-packages/taming/modules/vqvae/quantize.py)
Hi, can you once try upading the conda env using conda env update -f environment.yaml?
for me I was getting similar but different error, "ModuleNotFoundError: No module named 'optimizedSD'"
however, conda env update -f environment.yaml and conda update -n base -c defaults conda fixed it for me.
basujindal
